Certifying neural networks for autonomous aircraft

June 09, 2020 //By Nick Flaherty
Certifying neural networks for autonomous aircraft
In this video Dr Luuk Van Dijk, CEO of Swiss startup Daedalean talks to Ian Ferguson of software provider Lynx Software Technologies about the challenges of software for autonomous aircraft

Zurich-based Daedalean has written a 136 stage report with the European Union Aviation Safety Agency on assurance for the emergent properties of neural networks for autonomous aircraft.  

“A lot of frameworks are written for traditional avionics. What I want from my operating system is that it doesn’t sit between me and the bare metal,” said Luuk Van Dijk, CEO of Swiss startup Daedalean.

The company is working with Honeywell on a joint testing and technological partnership for autonomous aircraft for takeoff, landing and GPS-independent navigation and collision avoidance in electric vertical takeoff and landing vehicles (eVTOL).

The report is at www.easa.europa.eu/document-library/general-publications/concepts-design-assurance-neural-networks-codann

www.lynx.com

www.daedalean.ai

Related articles 


Vous êtes certain ?

Si vous désactivez les cookies, vous ne pouvez plus naviguer sur le site.

Vous allez être rediriger vers Google.